Semantic action recognition by learning a pose lexicon

作者：

Highlights：

• A novel semantic representation, pose lexicon, is proposed for action recognition.

• An extended hidden Markov alignment model is developed to learn a pose lexicon.

• A semantic action recognition method that is capable of zero-shot recognition is developed upon the lexicon.

• The efficacy of the proposed learning and recognition algorithms were evaluated on five datasets using cross-subject, cross-dataset and zero-shot protocols.

摘要

•A novel semantic representation, pose lexicon, is proposed for action recognition.•An extended hidden Markov alignment model is developed to learn a pose lexicon.•A semantic action recognition method that is capable of zero-shot recognition is developed upon the lexicon.•The efficacy of the proposed learning and recognition algorithms were evaluated on five datasets using cross-subject, cross-dataset and zero-shot protocols.

论文关键词：Lexicon,Semantic pose,Visual pose,Action recognition

论文评审过程：Received 31 January 2017, Revised 11 June 2017, Accepted 30 June 2017, Available online 1 July 2017, Version of Record 17 August 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.06.035